Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3422 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1120. Min Range: -0.1120

Max Act: 0.1086. Min Act: -0.0001

Data Index: 897444 (C4 (Web Text))

Max Activating Token Index: 18

Text #1

Max Range: 0.1120. Min Range: -0.1120

Max Act: 0.1067. Min Act: -0.0001

Data Index: 538269 (C4 (Web Text))

Max Activating Token Index: 449

Text #2

Max Range: 0.1120. Min Range: -0.1120

Max Act: 0.1051. Min Act: -0.0001

Data Index: 473755 (C4 (Web Text))

Max Activating Token Index: 522

Text #3

Max Range: 0.1120. Min Range: -0.1120

Max Act: 0.1120. Min Act: -0.0001

Data Index: 1032803 (C4 (Web Text))

Max Activating Token Index: 250

Text #4

Max Range: 0.1120. Min Range: -0.1120

Max Act: 0.1110. Min Act: -0.0001

Data Index: 1065632 (C4 (Web Text))

Max Activating Token Index: 116

Text #5

Max Range: 0.1120. Min Range: -0.1120

Max Act: 0.1056. Min Act: -0.0001

Data Index: 787538 (C4 (Web Text))

Max Activating Token Index: 168

Text #6

Max Range: 0.1120. Min Range: -0.1120

Max Act: 0.1006. Min Act: -0.0001

Data Index: 994878 (C4 (Web Text))

Max Activating Token Index: 152

Text #7

Max Range: 0.1120. Min Range: -0.1120

Max Act: 0.0927. Min Act: -0.0001

Data Index: 1239553 (C4 (Web Text))

Max Activating Token Index: 850

Text #8

Max Range: 0.1120. Min Range: -0.1120

Max Act: 0.0906. Min Act: -0.0001

Data Index: 582136 (C4 (Web Text))

Max Activating Token Index: 241

Text #9

Max Range: 0.1120. Min Range: -0.1120

Max Act: 0.0923. Min Act: -0.0001

Data Index: 469519 (C4 (Web Text))

Max Activating Token Index: 328

Text #10

Max Range: 0.1120. Min Range: -0.1120

Max Act: 0.0939. Min Act: -0.0001

Data Index: 287204 (C4 (Web Text))

Max Activating Token Index: 542

Text #11

Max Range: 0.1120. Min Range: -0.1120

Max Act: 0.0875. Min Act: -0.0001

Data Index: 1005208 (C4 (Web Text))

Max Activating Token Index: 927

Text #12

Max Range: 0.1120. Min Range: -0.1120

Max Act: 0.0872. Min Act: -0.0001

Data Index: 1149365 (C4 (Web Text))

Max Activating Token Index: 930

Text #13

Max Range: 0.1120. Min Range: -0.1120

Max Act: 0.0899. Min Act: -0.0001

Data Index: 928954 (C4 (Web Text))

Max Activating Token Index: 547

Text #14

Max Range: 0.1120. Min Range: -0.1120

Max Act: 0.0853. Min Act: -0.0001

Data Index: 353128 (C4 (Web Text))

Max Activating Token Index: 710

Text #15

Max Range: 0.1120. Min Range: -0.1120

Max Act: 0.0834. Min Act: -0.0001

Data Index: 182801 (C4 (Web Text))

Max Activating Token Index: 962

Text #16

Max Range: 0.1120. Min Range: -0.1120

Max Act: 0.0820. Min Act: -0.0001

Data Index: 644143 (C4 (Web Text))

Max Activating Token Index: 760

Text #17

Max Range: 0.1120. Min Range: -0.1120

Max Act: 0.0850. Min Act: -0.0001

Data Index: 487915 (C4 (Web Text))

Max Activating Token Index: 201

Text #18

Max Range: 0.1120. Min Range: -0.1120

Max Act: 0.0856. Min Act: -0.0001

Data Index: 586228 (C4 (Web Text))

Max Activating Token Index: 943

Text #19

Max Range: 0.1120. Min Range: -0.1120

Max Act: 0.0857. Min Act: -0.0001

Data Index: 1341634 (C4 (Web Text))

Max Activating Token Index: 662